{"ID":2882866,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10074","arxiv_id":"2508.10074","title":"Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History","abstract":"The rapid advancement of large language models (LLMs) has led to the widespread adoption of AI-powered coding assistants integrated into a development environment. On one hand, low-latency code completion offers completion suggestions but is fundamentally constrained to the cursor's current position. On the other hand, chat-based editing can perform complex modifications, yet forces developers to stop their work, describe the intent in natural language, which causes a context-switch away from the code. This creates a suboptimal user experience, as neither paradigm proactively predicts the developer's next edit in a sequence of related edits. To bridge this gap and provide the seamless code edit suggestion, we introduce the task of Next Edit Prediction, a novel task designed to infer developer intent from recent interaction history to predict both the location and content of the subsequent edit. Specifically, we curate a high-quality supervised fine-tuning dataset and an evaluation benchmark for the Next Edit Prediction task. Then, we conduct supervised fine-tuning on a series of models and performed a comprehensive evaluation of both the fine-tuned models and other baseline models, yielding several novel findings. This work lays the foundation for a new interaction paradigm that proactively collaborate with developers by anticipating their following action, rather than merely reacting to explicit instructions. The code is available at https://github.com/lurf21/NextEditPrediction.","short_abstract":"The rapid advancement of large language models (LLMs) has led to the widespread adoption of AI-powered coding assistants integrated into a development environment. On one hand, low-latency code completion offers completion suggestions but is fundamentally constrained to the cursor's current position. On the other hand,...","url_abs":"https://arxiv.org/abs/2508.10074","url_pdf":"https://arxiv.org/pdf/2508.10074v2","authors":"[\"Ruofan Lu\",\"Yintong Huo\",\"Meng Zhang\",\"Yichen Li\",\"Michael R. Lyu\"]","published":"2025-08-13T15:52:03Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":610927,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2882866,"paper_url":"https://arxiv.org/abs/2508.10074","paper_title":"Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History","repo_url":"https://github.com/lurf21/NextEditPrediction","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}